AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-preserving Model-based Deep Learning

TL;DR

AID-DTI is a novel deep learning framework that accelerates diffusion tensor imaging by accurately reconstructing detailed parametric maps from sparse data, effectively reducing noise and preserving fine structures.

Contribution

The paper introduces a new SVD-based regularizer and an adaptive learning algorithm for improved DTI reconstruction with fewer measurements, enhancing detail preservation and noise suppression.

Findings

Outperforms state-of-the-art methods in accuracy and detail preservation

Successfully reconstructs DTI maps from only six measurements

Demonstrates robustness on Human Connectome Project data

Abstract

Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and eddy current, leading to detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. To address this, this paper proposes a novel method, AID-DTI (\textbf{A}ccelerating h\textbf{I}gh fi\textbf{D}elity \textbf{D}iffusion \textbf{T}ensor \textbf{I}maging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition-based regularizer, which can effectively capture fine details while suppressing noise during network training by exploiting the correlation across DTI-derived parameters. Additionally, we introduce a Nesterov-based adaptive learning algorithm that optimizes the regularization parameter dynamically to enhance the performance. AID-DTI is an extendable framework capable of incorporating flexible network architecture. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms other state-of-the-art methods both quantitatively and qualitatively.